An Introduction to GC3Pie Session-based scripts. Riccardo Murri
|
|
- Arlene Edwards
- 6 years ago
- Views:
Transcription
1 An Introduction to GC3Pie Session-based scripts Riccardo Murri 04/04/2016
2 What is GC3Pie? GC3Pie is An opinionated Python framework for defining and running computational workflows; 2. A rapid development toolkit for running user applications on clusters and IaaS cloud resources; 3. The worst name ever given to a middleware piece... As users, you re mostly interested in this part. GC3Pie Tools University of Zurich, S3IT 04/04/2016
3 What is GC3Pie? GC3Pie is An opinionated Python framework for defining and running computational workflows; 2. A rapid development toolkit for running user applications on clusters and IaaS cloud resources; 3. The worst name ever given to a middleware piece... As users, you re mostly interested in this part. GC3Pie Tools University of Zurich, S3IT 04/04/2016
4 Who am I? Systems administrator and programmer. At UZH since 2010, first at GC3 then at S3IT. Developer of GC3Pie since GC3Pie Tools University of Zurich, S3IT 04/04/2016
5 and what about you? GC3Pie Tools University of Zurich, S3IT 04/04/2016
6 Outline of this training, 1 1. Concepts and glossary 2. Usage of a session-based script 3. Command-line tools mainly useful for debugging GC3Pie Tools University of Zurich, S3IT 04/04/2016
7 Outline of this training, 2 We d like the training to be as interactive and informal as possible. If you have a question, just ask don t wait. GC3Pie Tools University of Zurich, S3IT 04/04/2016
8 Concepts and glossary
9 GC3Pie glossary: Application GC3Pie runs user applications on clusters and IaaS cloud resources An Application is just a command to execute.
10 GC3Pie glossary: Application GC3Pie runs user applications on clusters and IaaS cloud resources An Application is just a command to execute. If you can run it in the terminal, you can run it in GC3Pie.
11 GC3Pie glossary: Application GC3Pie runs user applications on clusters and IaaS cloud resources An Application is just a command to execute. A single execution of an Application is indeed called a Run. (Other systems might call this a Job.)
12 GC3Pie glossary: Task GC3Pie runs user applications on clusters and IaaS cloud resources More generally, GC3Pie runs Tasks. Tasks are a superset of applications, in that they include workflows. More on this later!
13 GC3Pie glossary: Resources GC3Pie runs user applications on clusters and IaaS cloud resources Resources are the computing infrastructures where GC3Pie executes applications. Resources include: your laptop, the Hydra cluster, the Science Cloud, Amazon AWS.
14 The gservers command The gservers command is used to see configured and available resources. > gservers localhost frontend ( Frontend host name ) localhost type ( Access mode ) shellcmd updated ( Accessible? ) True queued ( Total queued jobs ) 0 user_queued ( Own queued jobs ) 0 user_run ( Own running jobs ) 6 max_cores_per_job ( Max cores per job ) 4 max_memory_per_core ( Max memory per core ) 8GiB max_walltime ( Max walltime per job ) 8hour Resources are defined in file $HOME/.gc3/gc3pie.conf Examples of resource definitions
15 The gservers command The gservers command is used to see configured and available resources. > gservers localhost frontend ( Frontend host name ) localhost type ( Access mode ) shellcmd updated ( Accessible? ) True queued ( Total queued jobs ) 0 user_queued ( Own queued jobs ) 0 user_run ( Own running jobs ) 6 max_cores_per_job ( Max cores per job ) 4 max_memory_per_core ( Max memory per core ) 8GiB max_walltime ( Max walltime per job ) 8hour Resources are defined in file $HOME/.gc3/gc3pie.conf Examples of resource definitions
16 Warholize! >./warholize.py uzh-logo.png -C 1
17 Session-based scripts warholize.py is a typical session-based script. A session is just a named collection of jobs. A session-based script creates a session and runs all the jobs in it until completion.
18 What GC3Pie handles for you 1. Resource allocation (e.g. starting new instances on ScienceCloud) 2. Selection of resources for each application in the session 3. Data transfer (e.g. copying input files in the new instances) 4. Remote execution of the application 5. Retrieval of results (e.g. copying output files from the running instance) 6. De-allocation of resources
19 Create a session A session-based script creates a session and runs all the jobs in it until completion. Create session logo-session: >./warholize.py uzh-logo.png -s logo-session
20 Run a session until done A session-based script creates a session and runs all the jobs in it until completion. Run jobs in session logo-session, polling for updates every 5 seconds: >./warholize.py -s logo-session --watch 5 You can stop a GC3Pie script by pressing Ctrl+C. Run it again to resume activity from where it stopped.
21 Run a session until done A session-based script creates a session and runs all the jobs in it until completion. Run jobs in session logo-session, polling for updates every 5 seconds: >./warholize.py -s logo-session --watch 5 You can stop a GC3Pie script by pressing Ctrl+C. Run it again to resume activity from where it stopped.
22 Alternate display of session contents, I Display top-level tasks in session logo-session: > gsession list logo-session Exercise : Now try it yourself.
23 WTF?? > gsession list warholize gc3.gc3libs: WARNING: Failed loading file /home/ubuntu/warholize/jobs/warholizeworkflow LoadError: Failed retrieving object from file /home/ubuntu/warholize/jobs/warholizeworkflow gc3.gc3libs: WARNING: Ignoring error from loading ParallelTaskCollection.107 : Failed retri JobID Job name State Info In order to work, all GC3Pie utilities need to access the Python script that generated the tasks and session. To fix: set the PYTHONPATH variable to the directory containing your script: > export PYTHONPATH=$PWD
24 WTF?? > gsession list warholize gc3.gc3libs: WARNING: Failed loading file /home/ubuntu/warholize/jobs/warholizeworkflow LoadError: Failed retrieving object from file /home/ubuntu/warholize/jobs/warholizeworkflow gc3.gc3libs: WARNING: Ignoring error from loading ParallelTaskCollection.107 : Failed retri JobID Job name State Info In order to work, all GC3Pie utilities need to access the Python script that generated the tasks and session. To fix: set the PYTHONPATH variable to the directory containing your script: > export PYTHONPATH=$PWD
25 Alternate display of session contents, II Display all tasks in session logo-session: > gsession list --recursive logo-session Workflows and task hierarchy
26 Alternate display of session contents, III Display summary of tasks in session logo-session: > gstat -n -b -s logo-session
27 Display session history Show log of activity on tasks in session logo-session: > gsession log logo-session
28 Select execution resource Select where applications will be run with option -r: >./warholize.py -s logo-session -r localhost The resource name must exists in the configuration file (i.e., check gservers output). Stopping a script and re-starting it with a different resource will likely result in an error: old tasks can no longer be found.
29 Limit concurrently-running jobs Limit the maximum number of concurrently-running tasks with option -J: >./warholize.py -s logo-session -J 1 In large computational campaigns, it is important not to flood the execution resources with too many tasks.
30 The output directory If you don t specify an output directory for your job, a session-based script collects output in the current working directory (but this can change from script to script). If an output directory already exists, it will be renamed and never overwritten. If you pass the option -o DIRECTORY to the script, all the output dirs will be saved inside that directory.
31 Passing requirements to the application Some options are used to specify some requirements of all applications in a session: -c NUM Set the number of CPU cores required for each job. -m GB Set the amount of memory required per execution core -w DURATION Set the time limit for each job; default is script-dependent. These options have proven not to be much useful except for debugging/experimentation, so they might be removed in a future release!
32 Session management
33 Aborting a single task To stop and abort a single task, use the gkill command: > gkill -s logo-session MyApplication.123 Exercise : What happens if you try to abort a task collection?
34 Aborting a whole session Kill all the running tasks in a session again using the gkill command: > gkill -s logo-session -A (GC3Pie also features a gsession abort command, but it s broken in the current release.)
35 Selecting tasks from a session, I The gselect command is the go-to tool for selective listing of tasks in a session. For example, to list finished tasks: > gselect -s logo-session --state TERMINATED The output of gselect is a list of task, IDs, to be fed into another GC3Pie command. For example, to kill all queued tasks: > gselect -s logo-session --state SUBMITTED xargs gkill -s logo-session
36 Selecting tasks from a session, II The gselect command has many different options to select tasks: > gselect --help usage: gselect [-h] [-V] [-v] [--config-files CONFIG_FILES] -s SESSION [--error-message REGEXP] [--input-file FILENAME] [--jobname REGEXP] [--jobid REGEXP] [-l STATES] [--output-file FILENAME] [--output-message REGEXP] [--successful] [--submitted-after DATE] [--submitted-before DATE] [--unsuccessful] Exercise : Use gselect to print the IDs of the TricolorizeImage tasks in the last Warholize session.
37 Thank you! Any questions?
38 Resource definition
39 Example execution resources: local host Allow GC3Pie to run tasks on the local computer. This is the default installed by GC3Pie into $HOME/.gc3/gc3pie.conf [resource/localhost] enabled = yes type = shellcmd frontend = localhost transport = local max_cores_per_job = 2 max_memory_per_core = 2GiB max_walltime = 8 hours max_cores = 2 architecture = x86_64 auth = none override = no
40 Example execution resources: SLURM Allow submission of jobs to the Hydra cluster. [resource/hydra] enabled = yes type = slurm frontend = login.s3it.uzh.ch transport = ssh auth = ssh_user_rmurri max_walltime = 1 day max_cores = 96 max_cores_per_job = 64 max_memory_per_core = 1 TiB architecture = x86_64 prologue_content = module load cluster/largemem [auth/ssh_user_ubuntu] type=ssh username=rmurri
41 Example execution resources: OpenStack [resource/sciencecloud] enabled=no type=openstack+shellcmd auth=openstack vm_pool_max_size = 32 security_group_name=default security_group_rules= tcp:22:22: /0, icmp:-1:-1: /0 network_ids= c86b320c a951-c8a068894cc2 [auth/ssh_user_ubuntu] # default user on Ubuntu VM images type=ssh username=ubuntu [auth/openstack] # only need to set the type here; # any other value will be taken from # the OS_* environment variables type = openstack # definition of a single execution VM instance_type=1cpu-4ram-hpc image_id=acebe825-e0d4-44ee-a1dc-a831561a2ea9 max_cores_per_job = 8 max_memory_per_core = 4 GiB max_walltime = 90 days max_cores = 32 architecture = x86_64 # how to connect vm_auth=ssh_user_ubuntu keypair_name=rmurri public_key=~/.ssh/id_dsa.pub
42 Workflows
43 The Warholize workflow How do we warholize an arbitrary image? 1. Convert the original image to grayscale. 2. Colorize the grayscale image using three different colors for each tile. 3. Arrange all the colorized images into an N N frame. Reference: tutorials/warholize/warholize.html
44 GC3Pie glossary: Task Collections The basic unit of work in a GC3Pie workflow is called a Task. The Application class that you already know is a kind of Task (in programming speak, it s a derived class). A set of Tasks is itself a Task, and is called a TaskCollection.
45 Running tasks in sequence To run tasks in an ordered sequence, one after the other, GC3Pie provides a SequentialTaskCollection class. It is created with a list of tasks, and runs all of them in the order given. The sequence is dynamic, in that you can add new tasks on the fly, re-run existing ones, or remove future tasks. A SequentialTaskCollection is itself a task.
46 Running tasks in parallel To run tasks in parallel (i.e., they have no inter-dependency), GC3Pie provides a ParallelTaskCollection class. It is created with a list of tasks, and runs all of them in parallel (compatibly with the computational resource limits). A ParallelTaskCollection is itself a task.
47 Putting it all together So tasks can be: Application instances, SequentialTaskCollections, ParallelTaskCollections. So you can nest them, and create parallelly-running sequences, or sequences of job explosions (many jobs in parallel), or any combination of this.
48 The Warholize workflow, I 1. Convert the original image to grayscale.
49 The Warholize workflow, II 2. Colorize the grayscale image using three different colors for each tile.
50 The Warholize workflow, III 3. Arrange all the colorized images into an N N frame.
51 The Warholize workflow, IV Step 2 actually entails two sub-steps: a) mapping greyscale levels to random colors, b) applying this mapping to produce new images
52 The Warholize workflow, V So, Step 2 is a SequentialTaskCollection-type task. Let s call this two-pass sequence TricolorizeImage. TricolorizeImage TricolorizeImage TricolorizeImage
53 The Warholize workflow, VI All the TricolorizeImage instances run in parallel. Collect them into a ParallelTaskCollection-type task, called TricolorizeMultipleImages. TricolorizeMultipleImages
54 The Warholize workflow, VII Now we are left with a three-step sequence: greyscale, TricolorizeMultipleImages, montage. This can be defined again as a SequentialTaskCollection-type task, the WarholizeWorkflow. WarholizeWorkflow
55 Appendix
New User Seminar: Part 2 (best practices)
New User Seminar: Part 2 (best practices) General Interest Seminar January 2015 Hugh Merz merz@sharcnet.ca Session Outline Submitting Jobs Minimizing queue waits Investigating jobs Checkpointing Efficiency
More informationPoS(EGICF12-EMITC2)143
GC3Pie: A Python framework for high-throughput computing GC3: Grid Computing Competence Center University of Zurich E-mail: sergio.maffioletti@gc3.uzh.ch Riccardo Murri GC3: Grid Computing Competence Center
More informationElastiCluster Automated provisioning of computational clusters in the cloud
ElastiCluster Automated provisioning of computational clusters in the cloud Riccardo Murri (with contributions from Antonio Messina, Nicolas Bär, Sergio Maffioletti, and Sigve
More informationgc3pie Documentation Release development (SVN Revision) Sergio Maffioletti, Antonio Messina, Mark Monroe, Riccardo Mur
gc3pie Documentation Release development (SVN Revision) Sergio Maffioletti, Antonio Messina, Mark Monroe, Riccardo Mur August 23, 2015 Contents 1 Introduction 1 2 Table of Contents 3 2.1 User Documentation.........................................
More informationPart2: Let s pick one cloud IaaS middleware: OpenStack. Sergio Maffioletti
S3IT: Service and Support for Science IT Cloud middleware Part2: Let s pick one cloud IaaS middleware: OpenStack Sergio Maffioletti S3IT: Service and Support for Science IT, University of Zurich http://www.s3it.uzh.ch/
More informationNote: Who is Dr. Who? You may notice that YARN says you are logged in as dr.who. This is what is displayed when user
Run a YARN Job Exercise Dir: ~/labs/exercises/yarn Data Files: /smartbuy/kb In this exercise you will submit an application to the YARN cluster, and monitor the application using both the Hue Job Browser
More informationSlurm basics. Summer Kickstart June slide 1 of 49
Slurm basics Summer Kickstart 2017 June 2017 slide 1 of 49 Triton layers Triton is a powerful but complex machine. You have to consider: Connecting (ssh) Data storage (filesystems and Lustre) Resource
More informationHigh Performance Computing (HPC) Club Training Session. Xinsheng (Shawn) Qin
High Performance Computing (HPC) Club Training Session Xinsheng (Shawn) Qin Outline HPC Club The Hyak Supercomputer Logging in to Hyak Basic Linux Commands Transferring Files Between Your PC and Hyak Submitting
More informationIntroduction to GALILEO
Introduction to GALILEO Parallel & production environment Mirko Cestari m.cestari@cineca.it Alessandro Marani a.marani@cineca.it Domenico Guida d.guida@cineca.it Maurizio Cremonesi m.cremonesi@cineca.it
More informationTransient Compute ARC as Cloud Front-End
Digital Infrastructures for Research 2016 2016-09-29, 11:30, Cracow 30 min slot AEC ALBERT EINSTEIN CENTER FOR FUNDAMENTAL PHYSICS Transient Compute ARC as Cloud Front-End Sigve Haug, AEC-LHEP University
More informationTable of Contents. Table of Contents Job Manager for remote execution of QuantumATK scripts. A single remote machine
Table of Contents Table of Contents Job Manager for remote execution of QuantumATK scripts A single remote machine Settings Environment Resources Notifications Diagnostics Save and test the new machine
More informationBatch Systems. Running calculations on HPC resources
Batch Systems Running calculations on HPC resources Outline What is a batch system? How do I interact with the batch system Job submission scripts Interactive jobs Common batch systems Converting between
More informationIntroduction to Abel/Colossus and the queuing system
Introduction to Abel/Colossus and the queuing system November 14, 2018 Sabry Razick Research Infrastructure Services Group, USIT Topics First 7 slides are about us and links The Research Computing Services
More informationQuick Guide for the Torque Cluster Manager
Quick Guide for the Torque Cluster Manager Introduction: One of the main purposes of the Aries Cluster is to accommodate especially long-running programs. Users who run long jobs (which take hours or days
More informationExeco tutorial Grid 5000 school, Grenoble, January 2016
Execo tutorial Grid 5000 school, Grenoble, January 2016 Simon Delamare Matthieu Imbert Laurent Pouilloux INRIA/CNRS/LIP ENS-Lyon 03/02/2016 1/34 1 introduction 2 execo, core module 3 execo g5k, Grid 5000
More informationIntroduction to the Cluster
Introduction to the Cluster Advanced Computing Center for Research and Education http://www.accre.vanderbilt.edu Follow us on Twitter for important news and updates: @ACCREVandy The Cluster We will be
More informationIntroduction to PICO Parallel & Production Enviroment
Introduction to PICO Parallel & Production Enviroment Mirko Cestari m.cestari@cineca.it Alessandro Marani a.marani@cineca.it Domenico Guida d.guida@cineca.it Nicola Spallanzani n.spallanzani@cineca.it
More informationIntroduction to the Cluster
Follow us on Twitter for important news and updates: @ACCREVandy Introduction to the Cluster Advanced Computing Center for Research and Education http://www.accre.vanderbilt.edu The Cluster We will be
More informationIntroduction to High Performance Computing Using Sapelo2 at GACRC
Introduction to High Performance Computing Using Sapelo2 at GACRC Georgia Advanced Computing Resource Center University of Georgia Suchitra Pakala pakala@uga.edu 1 Outline High Performance Computing (HPC)
More informationDuke Compute Cluster Workshop. 3/28/2018 Tom Milledge rc.duke.edu
Duke Compute Cluster Workshop 3/28/2018 Tom Milledge rc.duke.edu rescomputing@duke.edu Outline of talk Overview of Research Computing resources Duke Compute Cluster overview Running interactive and batch
More informationA Hands on Introduction to Docker
A Hands on Introduction to Docker Len Bass A Hands on introduction Introduction to to Docker May 2017 1 4, Len 2017 Bass 2017 Len Bass 1 Setting expectations This is an introduction to Docker intended
More informationImage Sharpening. Practical Introduction to HPC Exercise. Instructions for Cirrus Tier-2 System
Image Sharpening Practical Introduction to HPC Exercise Instructions for Cirrus Tier-2 System 2 1. Aims The aim of this exercise is to get you used to logging into an HPC resource, using the command line
More informationAN INTRODUCTION TO WORKFLOWS WITH DAGMAN
AN INTRODUCTION TO WORKFLOWS WITH DAGMAN Presented by Lauren Michael HTCondor Week 2018 1 Covered In This Tutorial Why Create a Workflow? Describing workflows as directed acyclic graphs (DAGs) Workflow
More informationQosCosGrid Middleware
Domain-oriented services and resources of Polish Infrastructure for Supporting Computational Science in the European Research Space PLGrid Plus QosCosGrid Middleware Domain-oriented services and resources
More informationHigh Performance Computing Cluster Basic course
High Performance Computing Cluster Basic course Jeremie Vandenplas, Gwen Dawes 30 October 2017 Outline Introduction to the Agrogenomics HPC Connecting with Secure Shell to the HPC Introduction to the Unix/Linux
More informationIntroduction to High-Performance Computing (HPC)
Introduction to High-Performance Computing (HPC) Computer components CPU : Central Processing Unit cores : individual processing units within a CPU Storage : Disk drives HDD : Hard Disk Drive SSD : Solid
More informationDCLI User's Guide. Data Center Command-Line Interface 2.9.1
Data Center Command-Line Interface 2.9.1 You can find the most up-to-date technical documentation on the VMware website at: https://docs.vmware.com/ If you have comments about this documentation, submit
More informationIntel Manycore Testing Lab (MTL) - Linux Getting Started Guide
Intel Manycore Testing Lab (MTL) - Linux Getting Started Guide Introduction What are the intended uses of the MTL? The MTL is prioritized for supporting the Intel Academic Community for the testing, validation
More informationMigrating from Zcluster to Sapelo
GACRC User Quick Guide: Migrating from Zcluster to Sapelo The GACRC Staff Version 1.0 8/4/17 1 Discussion Points I. Request Sapelo User Account II. III. IV. Systems Transfer Files Configure Software Environment
More informationZeroVM Package Manager Documentation
ZeroVM Package Manager Documentation Release 0.2.1 ZeroVM Team October 14, 2014 Contents 1 Introduction 3 1.1 Creating a ZeroVM Application..................................... 3 2 ZeroCloud Authentication
More informationDCLI User's Guide. Data Center Command-Line Interface 2.7.0
Data Center Command-Line Interface 2.7.0 You can find the most up-to-date technical documentation on the VMware Web site at: https://docs.vmware.com/ The VMware Web site also provides the latest product
More informationLab 2 Third Party API Integration, Cloud Deployment & Benchmarking
Lab 2 Third Party API Integration, Cloud Deployment & Benchmarking In lab 1, you have setup the web framework and the crawler. In this lab, you will complete the deployment flow for launching a web application
More informationUsing Compute Canada. Masao Fujinaga Information Services and Technology University of Alberta
Using Compute Canada Masao Fujinaga Information Services and Technology University of Alberta Introduction to cedar batch system jobs are queued priority depends on allocation and past usage Cedar Nodes
More informationArcGIS Enterprise: Advanced Topics in Administration. Thomas Edghill & Moginraj Mohandas
ArcGIS Enterprise: Advanced Topics in Administration Thomas Edghill & Moginraj Mohandas Outline Overview: Base ArcGIS Enterprise Deployment - Key Components - Administrator Endpoints Advanced Workflows:
More informationHOD User Guide. Table of contents
Table of contents 1 Introduction...3 2 Getting Started Using HOD... 3 2.1 A typical HOD session... 3 2.2 Running hadoop scripts using HOD...5 3 HOD Features... 6 3.1 Provisioning and Managing Hadoop Clusters...6
More informationIntroduction to Discovery.
Introduction to Discovery http://discovery.dartmouth.edu The Discovery Cluster 2 Agenda What is a cluster and why use it Overview of computer hardware in cluster Help Available to Discovery Users Logging
More informationHadoop On Demand User Guide
Table of contents 1 Introduction...3 2 Getting Started Using HOD... 3 2.1 A typical HOD session... 3 2.2 Running hadoop scripts using HOD...5 3 HOD Features... 6 3.1 Provisioning and Managing Hadoop Clusters...6
More information271 Waverley Oaks Rd. Telephone: Suite 206 Waltham, MA USA
Contacting Leostream Leostream Corporation http://www.leostream.com 271 Waverley Oaks Rd. Telephone: +1 781 890 2019 Suite 206 Waltham, MA 02452 USA To submit an enhancement request, email features@leostream.com.
More informationSubmitting batch jobs Slurm on ecgate Solutions to the practicals
Submitting batch jobs Slurm on ecgate Solutions to the practicals Xavi Abellan xavier.abellan@ecmwf.int User Support Section Com Intro 2015 Submitting batch jobs ECMWF 2015 Slide 1 Practical 1: Basic job
More informationNBIC TechTrack PBS Tutorial
NBIC TechTrack PBS Tutorial by Marcel Kempenaar, NBIC Bioinformatics Research Support group, University Medical Center Groningen Visit our webpage at: http://www.nbic.nl/support/brs 1 NBIC PBS Tutorial
More informationJozef Cernak, Marek Kocan, Eva Cernakova (P. J. Safarik University in Kosice, Kosice, Slovak Republic)
ARC tools for revision and nightly functional tests Jozef Cernak, Marek Kocan, Eva Cernakova (P. J. Safarik University in Kosice, Kosice, Slovak Republic) Outline Testing strategy in ARC ARC-EMI testing
More informationEasy Access to Grid Infrastructures
Easy Access to Grid Infrastructures Dr. Harald Kornmayer (NEC Laboratories Europe) On behalf of the g-eclipse consortium WP11 Grid Workshop Grenoble, France 09 th of December 2008 Background in astro particle
More informationA Virtual Comet. HTCondor Week 2017 May Edgar Fajardo On behalf of OSG Software and Technology
A Virtual Comet HTCondor Week 2017 May 3 2017 Edgar Fajardo On behalf of OSG Software and Technology 1 Working in Comet What my friends think I do What Instagram thinks I do What my boss thinks I do 2
More informationUser Guide of High Performance Computing Cluster in School of Physics
User Guide of High Performance Computing Cluster in School of Physics Prepared by Sue Yang (xue.yang@sydney.edu.au) This document aims at helping users to quickly log into the cluster, set up the software
More informationHow to Deploy Virtual Test Agents in OpenStack
How to Deploy Virtual Test Agents in OpenStack Executive Summary This guide explains how to deploy Netrounds Virtual Test Agents (vtas) in OpenStack and how to control these from Netrounds Control Center.
More informationDCLI User's Guide. Modified on 20 SEP 2018 Data Center Command-Line Interface
Modified on 20 SEP 2018 Data Center Command-Line Interface 2.10.0 You can find the most up-to-date technical documentation on the VMware website at: https://docs.vmware.com/ If you have comments about
More informationUsing Cartesius and Lisa. Zheng Meyer-Zhao - Consultant Clustercomputing
Zheng Meyer-Zhao - zheng.meyer-zhao@surfsara.nl Consultant Clustercomputing Outline SURFsara About us What we do Cartesius and Lisa Architectures and Specifications File systems Funding Hands-on Logging
More informationHPC Workshop. Nov. 9, 2018 James Coyle, PhD Dir. Of High Perf. Computing
HPC Workshop Nov. 9, 2018 James Coyle, PhD Dir. Of High Perf. Computing NEEDED EQUIPMENT 1. Laptop with Secure Shell (ssh) for login A. Windows: download/install putty from https://www.chiark.greenend.org.uk/~sgtatham/putty/latest.html
More informationUF Research Computing: Overview and Running STATA
UF : Overview and Running STATA www.rc.ufl.edu Mission Improve opportunities for research and scholarship Improve competitiveness in securing external funding Matt Gitzendanner magitz@ufl.edu Provide high-performance
More informationNETCONF Client GUI. Client Application Files APPENDIX
APPENDIX B The NETCONF client is a simple GUI client application that can be used to understand the implementation of the NETCONF protocol in Cisco E-DI. This appendix includes the following information:
More informationIntroduction to HPC Using zcluster at GACRC
Introduction to HPC Using zcluster at GACRC On-class STAT8330 Georgia Advanced Computing Resource Center University of Georgia Suchitra Pakala pakala@uga.edu Slides courtesy: Zhoufei Hou 1 Outline What
More informationHPC at UZH: status and plans
HPC at UZH: status and plans Dec. 4, 2013 This presentation s purpose Meet the sysadmin team. Update on what s coming soon in Schroedinger s HW. Review old and new usage policies. Discussion (later on).
More informationIntroduction to High-Performance Computing (HPC)
Introduction to High-Performance Computing (HPC) Computer components CPU : Central Processing Unit cores : individual processing units within a CPU Storage : Disk drives HDD : Hard Disk Drive SSD : Solid
More informationA Hands-On Tutorial: RNA Sequencing Using High-Performance Computing
A Hands-On Tutorial: RNA Sequencing Using Computing February 11th and 12th, 2016 1st session (Thursday) Preliminaries: Linux, HPC, command line interface Using HPC: modules, queuing system Presented by:
More informationBackpacking with Code: Software Portability for DHTC Wednesday morning, 9:00 am Christina Koch Research Computing Facilitator
Backpacking with Code: Software Portability for DHTC Wednesday morning, 9:00 am Christina Koch (ckoch5@wisc.edu) Research Computing Facilitator University of Wisconsin - Madison Understand the basics of...
More informationHigh Performance Computing Cluster Advanced course
High Performance Computing Cluster Advanced course Jeremie Vandenplas, Gwen Dawes 9 November 2017 Outline Introduction to the Agrogenomics HPC Submitting and monitoring jobs on the HPC Parallel jobs on
More informationManaging Deployment. Understanding Deployment CHAPTER
CHAPTER 8 The settings and policies you define in Security Manager must be deployed to your devices so that you can implement them in your network. The steps you take to deploy configurations to devices
More informationVMware vrealize Code Stream Reference Architecture. 16 MAY 2017 vrealize Code Stream 2.3
VMware vrealize Code Stream Reference Architecture 16 MAY 2017 vrealize Code Stream 2.3 You can find the most up-to-date technical documentation on the VMware website at: https://docs.vmware.com/ If you
More informationCondor and Workflows: An Introduction. Condor Week 2011
Condor and Workflows: An Introduction Condor Week 2011 Kent Wenger Condor Project Computer Sciences Department University of Wisconsin-Madison Outline > Introduction/motivation > Basic DAG concepts > Running
More informationWelcome to our walkthrough of Setting up an AWS EC2 Instance
Welcome to our walkthrough of Setting up an AWS EC2 Instance What is an EC2 Instance: An EC2 Instance is a virtual server in Amazon s Elastic Compute Cloud EC2 for running applications on AWS infrastructure.
More informationSTARTING THE DDT DEBUGGER ON MIO, AUN, & MC2. (Mouse over to the left to see thumbnails of all of the slides)
STARTING THE DDT DEBUGGER ON MIO, AUN, & MC2 (Mouse over to the left to see thumbnails of all of the slides) ALLINEA DDT Allinea DDT is a powerful, easy-to-use graphical debugger capable of debugging a
More informationUtilities. Introduction. Working with SCE Platform Files. Working with Directories CHAPTER
CHAPTER 4 Revised: September 27, 2012, Introduction This chapter describes the following utilities: Working with SCE Platform Files, page 4-1 The User Log, page 4-5 Managing Syslog, page 4-8 Flow Capture,
More informationDistributed Systems. 31. The Cloud: Infrastructure as a Service Paul Krzyzanowski. Rutgers University. Fall 2013
Distributed Systems 31. The Cloud: Infrastructure as a Service Paul Krzyzanowski Rutgers University Fall 2013 December 12, 2014 2013 Paul Krzyzanowski 1 Motivation for the Cloud Self-service configuration
More informationLogging in to the CRAY
Logging in to the CRAY 1. Open Terminal Cray Hostname: cray2.colostate.edu Cray IP address: 129.82.103.183 On a Mac 2. type ssh username@cray2.colostate.edu where username is your account name 3. enter
More informationSubmitting batch jobs
Submitting batch jobs SLURM on ECGATE Xavi Abellan Xavier.Abellan@ecmwf.int ECMWF February 20, 2017 Outline Interactive mode versus Batch mode Overview of the Slurm batch system on ecgate Batch basic concepts
More informationSCALABLE HYBRID PROTOTYPE
SCALABLE HYBRID PROTOTYPE Scalable Hybrid Prototype Part of the PRACE Technology Evaluation Objectives Enabling key applications on new architectures Familiarizing users and providing a research platform
More informationPlease include the following sentence in any works using center resources.
The TCU High-Performance Computing Center The TCU HPCC currently maintains a cluster environment hpcl1.chm.tcu.edu. Work on a second cluster environment is underway. This document details using hpcl1.
More informationUL HPC Monitoring in practice: why, what, how, where to look
C. Parisot UL HPC Monitoring in practice: why, what, how, where to look 1 / 22 What is HPC? Best Practices Getting Fast & Efficient UL HPC Monitoring in practice: why, what, how, where to look Clément
More informationSWIF SCIENTIFIC WORKFLOW INDEFATIGABLE FACTOTUM
SWIF SCIENTIFIC WORKFLOW INDEFATIGABLE FACTOTUM WHY? Optimize tape access Easily cancel / modify / retry jobs Specify inter-job dependencies Script-friendly Simplify batch system TERMS Workflow Named container
More informationPegasus. Automate, recover, and debug scientific computations. Rafael Ferreira da Silva.
Pegasus Automate, recover, and debug scientific computations. Rafael Ferreira da Silva http://pegasus.isi.edu Experiment Timeline Scientific Problem Earth Science, Astronomy, Neuroinformatics, Bioinformatics,
More informationJob Control Guide. Schrödinger Software Release Schrödinger Press
Job Control Guide Job Control Guide Schrödinger Software Release 2015-2 Schrödinger Press Job Control Guide Copyright 2015 Schrödinger, LLC. All rights reserved. While care has been taken in the preparation
More informationBIG-IP Virtual Edition and Cloud-Init. Version 13.0
BIG-IP Virtual Edition and Cloud-Init Version 13.0 Table of Contents Table of Contents About Cloud-Init and BIG-IP VE...5 About Cloud-Init and BIG-IP VE...5 Hypervisors with Cloud-Init support in BIG-IP
More informationWorkload management at KEK/CRC -- status and plan
Workload management at KEK/CRC -- status and plan KEK/CRC Hiroyuki Matsunaga Most of the slides are prepared by Koichi Murakami and Go Iwai CPU in KEKCC Work server & Batch server Xeon 5670 (2.93 GHz /
More informationAnswers to Federal Reserve Questions. Training for University of Richmond
Answers to Federal Reserve Questions Training for University of Richmond 2 Agenda Cluster Overview Software Modules PBS/Torque Ganglia ACT Utils 3 Cluster overview Systems switch ipmi switch 1x head node
More informationTechnical Brief. Network Port & Routing Requirements Active Circle 4.5 May Page 1 sur 15
Technical Brief Network Port & Routing Requirements Active Circle 4.5 May 2017 Page 1 sur 15 INDEX 1. INTRODUCTION... 3 1.1. SCOPE OF THE DOCUMENT... 3 1.2. AUDIENCE... 3 1.3. ORGANIZATION OF THE INFORMATION...
More informationSwiftrun i. Swiftrun
i Swiftrun ii Contents 1 Introduction 1 2 Running older Swift releases 1 2.1 sites.xml........................................................ 1 2.2 tc.data.........................................................
More informationand how to use TORQUE & Maui Piero Calucci
Queue and how to use & Maui Scuola Internazionale Superiore di Studi Avanzati Trieste November 2008 Advanced School in High Performance and Grid Computing Outline 1 We Are Trying to Solve 2 Using the Manager
More informationUoW HPC Quick Start. Information Technology Services University of Wollongong. ( Last updated on October 10, 2011)
UoW HPC Quick Start Information Technology Services University of Wollongong ( Last updated on October 10, 2011) 1 Contents 1 Logging into the HPC Cluster 3 1.1 From within the UoW campus.......................
More informationNew High Performance Computing Cluster For Large Scale Multi-omics Data Analysis. 28 February 2018 (Wed) 2:30pm 3:30pm Seminar Room 1A, G/F
New High Performance Computing Cluster For Large Scale Multi-omics Data Analysis 28 February 2018 (Wed) 2:30pm 3:30pm Seminar Room 1A, G/F The Team (Bioinformatics & Information Technology) Eunice Kelvin
More informationZipRecruiter Apply Webhook Documentation. ZR ATS Integration Team. Version 1.1,
ZipRecruiter Apply Webhook Documentation ZR ATS Integration Team Version 1.1, 2017-10-12 Table of Contents Introduction................................................................................ 1
More informationGPU Cluster Usage Tutorial
GPU Cluster Usage Tutorial How to make caffe and enjoy tensorflow on Torque 2016 11 12 Yunfeng Wang 1 PBS and Torque PBS: Portable Batch System, computer software that performs job scheduling versions
More informationSubmitting and running jobs on PlaFRIM2 Redouane Bouchouirbat
Submitting and running jobs on PlaFRIM2 Redouane Bouchouirbat Summary 1. Submitting Jobs: Batch mode - Interactive mode 2. Partition 3. Jobs: Serial, Parallel 4. Using generic resources Gres : GPUs, MICs.
More informationIntroduction to High-Performance Computing (HPC)
Introduction to High-Performance Computing (HPC) Computer components CPU : Central Processing Unit CPU cores : individual processing units within a Storage : Disk drives HDD : Hard Disk Drive SSD : Solid
More informationUPPMAX Introduction Martin Dahlö Valentin Georgiev
UPPMAX Introduction 2017-11-27 Martin Dahlö martin.dahlo@scilifelab.uu.se Valentin Georgiev valentin.georgiev@icm.uu.se Objectives What is UPPMAX what it provides Projects at UPPMAX How to access UPPMAX
More informationShark Cluster Overview
Shark Cluster Overview 51 Execution Nodes 1 Head Node (shark) 1 Graphical login node (rivershark) 800 Cores = slots 714 TB Storage RAW Slide 1/14 Introduction What is a cluster? A cluster is a group of
More informationData Store Management Best Practices. Bill Major Laurence Clinton
Data Store Management Best Practices Bill Major Laurence Clinton Session Agenda 1. Overview 2. Installation and Configuration 3. Backing up the data store 4. Restoring the data store 5. Moving data store
More informationClient tools know everything
Scheduling, clients Client tools know everything Application database Certificate Certificate Authorised users directory Certificate Policies Grid job management service Data Certificate Certificate Researcher
More informationLogging. About Logging. This chapter describes how to log system messages and use them for troubleshooting.
This chapter describes how to log system messages and use them for troubleshooting. About, page 1 Guidelines for, page 7 Configure, page 8 Monitoring the Logs, page 26 History for, page 29 About System
More informationChapter 5. Minimization of Average Completion Time and Waiting Time in Cloud Computing Environment
Chapter 5 Minimization of Average Completion Time and Waiting Time in Cloud Computing Cloud computing is the use of the Internet for the tasks the users performing on their computer. Cloud computing, also
More informationHortonworks Data Platform
Hortonworks Data Platform Workflow Management (August 31, 2017) docs.hortonworks.com Hortonworks Data Platform: Workflow Management Copyright 2012-2017 Hortonworks, Inc. Some rights reserved. The Hortonworks
More informationMERCED CLUSTER BASICS Multi-Environment Research Computer for Exploration and Discovery A Centerpiece for Computational Science at UC Merced
MERCED CLUSTER BASICS Multi-Environment Research Computer for Exploration and Discovery A Centerpiece for Computational Science at UC Merced Sarvani Chadalapaka HPC Administrator University of California
More informationAspera Connect Mac: OS X 10.6, 10.7, 10.8, Revision: Generated: 11/11/ :29
Aspera Connect 3.5.2 Mac: OS X 10.6, 10.7, 10.8, 10.9. 10.10 Revision: 3.5.2.95905 Generated: 11/11/2014 17:29 Contents 2 Contents Introduction... 3 System Requirements... 4 Setting up Connect... 5 Part
More informationBOSCO Architecture. Derek Weitzel University of Nebraska Lincoln
BOSCO Architecture Derek Weitzel University of Nebraska Lincoln Goals We want an easy to use method for users to do computational research It should be easy to install, use, and maintain It should be simple
More informationZend PHP Cloud Application Platform
Zend PHP Cloud Application Platform Kevin Schroeder Technology Evangelist About me Past: Programming/Sys Admin Current: Technology Evangelist/Author/Composer @kpschrade Is this a new product? No! It is
More informationGSS Administration and Troubleshooting
CHAPTER 9 GSS Administration and Troubleshooting This chapter covers the procedures necessary to properly manage and maintain your GSSM and GSS devices, including login security, software upgrades, GSSM
More informationMoodle Destroyer Tools Documentation
Moodle Destroyer Tools Documentation Release 0.0.1 Manly Man Dec 22, 2017 With Web Services 1 Features and Screenshots 3 2 Grading with Webservices 7 2.1 Prerequisites...............................................
More informationFileCruiser. Administrator Portal Guide
FileCruiser Administrator Portal Guide Contents Administrator Portal Guide Contents Login to the Administration Portal 1 Home 2 Capacity Overview 2 Menu Features 3 OU Space/Team Space/Personal Space Usage
More informationWelcome! Considering a Warm Disaster Recovery Site?
Welcome! Considering a Warm Disaster Recovery Site? Today s Moderator: Chris Riley Director 410-771-5544 x4331 criley@syssrc.com Today s Presenter: Rich Glenn Director 410-771-5544 x4420 rglenn@syssrc.com
More informationRedhat OpenStack 5.0 and PLUMgrid OpenStack Networking Suite 2.0 Installation Hands-on lab guide
Redhat OpenStack 5.0 and PLUMgrid OpenStack Networking Suite 2.0 Installation Hands-on lab guide Oded Nahum Principal Systems Engineer PLUMgrid EMEA November 2014 Page 1 Page 2 Table of Contents Table
More informationVMware vrealize Code Stream Reference Architecture. 12 APRIL 2018 vrealize Code Stream 2.4
VMware vrealize Code Stream Reference Architecture 12 APRIL 2018 vrealize Code Stream 2.4 You can find the most up-to-date technical documentation on the VMware website at: https://docs.vmware.com/ If
More information